Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    risks and consequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     அல்லது
    0.49
    他の
    0.48
     někter
    0.46
    或
    0.46
     undergraduate
    0.42
     proposals
    0.42
     measurements
    0.42
     或
    0.41
     উদ্ভি
    0.41
     clashes
    0.41
    POSITIVE LOGITS
    Team
    0.49
     hijas
    0.46
    笑顔
    0.46
     للصف
    0.45
    Teams
    0.43
    솎
    0.42
     mutlu
    0.41
     ٹیم
    0.41
     жиз
    0.41
     подар
    0.40
    Act Density 0.006%

    No Known Activations